Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     strengthening
    0.38
     arrêté
    0.38
     hör
    0.38
     بەر
    0.38
    ാം
    0.37
     Uma
    0.37
     pretends
    0.36
     boldly
    0.36
    ST
    0.36
    Din
    0.36
    POSITIVE LOGITS
     मैट
    0.61
    matte
    0.58
     Mat
    0.56
     mat
    0.55
     materias
    0.53
    Mat
    0.52
     матери
    0.51
     Matilda
    0.51
     मटे
    0.51
     мате
    0.50
    Act Density 0.007%

    No Known Activations